Port of OpenAI's Whisper model in C/C++

stb single-file public domain libraries for C/C++

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

*That Project's project repository

Open-Source Large Vocabulary Continuous Speech Recognition Engine

Efficient neural speech synthesis

Speech recognition tool to convert audio to text transcripts, for Linux and Raspberry Pi.

Simple Speech-To-Text on the '10 cents' CH32V003 Microcontroller

This is an enhancement fork with the explicit aim of supporting current shipping Raspbian/Ubuntu kernels without requiring downgrading. Please donate at https://hintak.github.io/ if it works for yo…

Improved SVOX PicoTTS speech synthesizer

vad algorithm based on esp32 for mute detection

2 channel delay sum beamformer

PlatformIO component for TFLM spectrogram features from audio samples

Python library to detect CPU SIMD capabilities.